Hero Figures

The Science of Startups: The Impact of Founder Personalities on Company Success # 2024-01-16, Xian Gong Output:

• Employees vs Entrepreneurs Random Forest model confusion matrix (Fig 1A)
• Employees vs Entrepreneurs Distribution of big 5 facets (Figure 1B)
• t-SNE 2D plot with six clusters (Figure 1C)
• Dendrogram heat map of facets per cluster (Figure 1D)

import pandas as pd
import numpy as np

import matplotlib.pyplot as plt
import matplotlib.patheffects as PathEffects
from matplotlib.collections import PolyCollection
from matplotlib.colors import to_rgb
import seaborn as sns

from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.model_selection import StratifiedKFold, GridSearchCV, RandomizedSearchCV, cross_val_score
from sklearn.metrics import accuracy_score
from sklearn.metrics import f1_score
from sklearn.metrics import fbeta_score
from sklearn.metrics import log_loss
from sklearn.metrics import roc_auc_score
from sklearn.metrics import confusion_matrix

import plotly
import plotly.express as px
import plotly.io as pio
import plotly.graph_objects as go

from sklearn.preprocessing import scale
import scipy
from random import random
import pandas.testing as tm

from pyclustertend import hopkins

import scipy.cluster.hierarchy as sch
from sklearn.manifold import TSNE
import time

from sklearn import datasets
from palmerpenguins import load_penguins

from sklearn.metrics import davies_bouldin_score
from sklearn.metrics import silhouette_score
from sklearn.metrics import calinski_harabasz_score
from validclust import dunn

from sklearn.metrics import pairwise_distances

from sklearn.cluster import AgglomerativeClustering
import statsmodels.api as sm

# Figure Quality
%matplotlib inline
plt.rcParams['figure.dpi'] = 300

Main

Figure 1A (Employees vs Entrepreneurs Random Forest model confusion matrix)

It takes forever to run the code so I take smaller samples here.

# Load the data
df_input = pd.read_csv('Entrepreneurs_and_Employee_Scores_Anon.csv')
df_input = df_input.set_index('User')

df_input = df_input.sample(500)

# Load the data
#df_input = pd.read_csv('11085_Entrepreneurs_and_Employee_Percentile_Scores.csv')
#df_input = df_input.set_index('User')

# Train Test Split
X_train, X_test, y_train, y_test = train_test_split(df_input.iloc[:,:-1], df_input.iloc[:,[-1]], test_size=0.3, random_state=42)

# Tuning hyperparameters of SVM
# List of C values
C_range = np.logspace(-1, 1, 3)
print(f'The list of values for C are {C_range}')
# List of gamma values
gamma_range = np.logspace(-1, 1, 3)
print(f'The list of values for gamma are {gamma_range}')

The list of values for C are [ 0.1  1.  10. ]
The list of values for gamma are [ 0.1  1.  10. ]

Comment

The following code takes very long to run:

# SVM Classifier
# Define the search space
param_grid = { 
    # Regularization parameter.
    "C": C_range,
    # Kernel type
    "kernel": ['rbf', 'poly'],
    # Gamma is the Kernel coefficient for ‘rbf’, ‘poly’ and ‘sigmoid’.
    "gamma": gamma_range.tolist()+['scale', 'auto']
    }
# Set up score
scoring = ['roc_auc']
# Set up the k-fold cross-validation
kfold = StratifiedKFold(n_splits=2, shuffle=True, random_state=0)

svc = SVC(probability=True)
# Define grid search
grid_search = GridSearchCV(estimator=svc, 
                           param_grid=param_grid, 
                           scoring=scoring, 
                           refit='roc_auc', 
                           n_jobs=-1, 
                           cv=kfold, 
                           verbose=0)
# Fit grid search
grid_result = grid_search.fit(X_train, y_train)

# Model Performance
print(f'The best accuracy score for the training dataset is {grid_result.best_score_:.4f}')
print(f'The best hyperparameters are {grid_result.best_params_}')
print(f'The accuracy score for the testing dataset is {grid_search.score(X_test, y_test):.4f}')

# Test set Performance
svm_best_model = grid_result.best_estimator_

y_pred_svm = svm_best_model.predict(X_test)
y_pred_log_proba_svm = svm_best_model.predict_log_proba(X_test)
y_pred_proba_svm = svm_best_model.predict_proba(X_test)

accuracy_svm = accuracy_score(y_test, y_pred_svm)
f1_svm = f1_score(y_test, y_pred_svm, average='weighted')
auc_svm = roc_auc_score(y_test, y_pred_proba_svm[:, 1])

CM_svm = confusion_matrix(y_test,y_pred_svm)
TN_svm = CM_svm[0][0]
FN_svm = CM_svm[1][0] 
TP_svm = CM_svm[1][1]
FP_svm = CM_svm[0][1]

specificity_svm = round(TN_svm / (TN_svm+FP_svm),4 ) 
ppv_svm = round(TP_svm / (TP_svm+FP_svm),4 )

print ("Accuracy score: {0}".format(accuracy_svm))
print ("F1 score: {0}".format(f1_svm))
print ("Specificity: {0}".format(specificity_svm))
print ("Positive Predictive Value: {0}".format(ppv_svm))
print ("AUC score: {0}".format(auc_svm))

# Figure 1A
data = (CM_svm/CM_svm.sum(axis = 1)).tolist()
fig = px.imshow(data,
                labels=dict(x="<b>Predicted Label</b>", y="<b>True Label</b>", color="Percent", fontsize = 14),
                x=['Employee', 'Entrepreneur'],
                y=['Employee', 'Entrepreneur'], 
#                 color_continuous_scale = px.colors.sequential.Blugrn, 
                color_continuous_scale = px.colors.sequential.Greens, 
                template = 'simple_white', 
                text_auto='.2f')
fig.update_xaxes(side="top")

fig.update_coloraxes(colorbar_thickness = 30, 
                     colorbar_tickfont = dict(size = 20),
                     colorbar_len = 0.6, 
                     colorbar_ticklabelposition = 'outside top')

fig.update_layout(margin = dict(t=200,r=200,b=200,l=200),
    xaxis = dict(linecolor = 'white'),
    yaxis = dict(linecolor = 'white'),
    showlegend = False,
    width = 700, height = 700,
    autosize = False )

fig.update_layout(
    font=dict(
        size=14,  # Set the font size here
    )
)

fig.update_layout(
    margin=dict(r=0, b=0, t = 0, l=0,pad=20)
)

# fig.update_layout(

# #     xaxis=dict(gridcolor='lightgrey'),
#     margin=dict(r=2, b=50, pad=10)
# )


#x axis
# fig.update_xaxes(visible=False)

#y axis    
# fig.update_yaxes(visible=False)
fig.show()
# fig.write_image("outputFiles/Figure_2a.pdf")

Figure 1B (Employees vs Entrepreneurs Distribution of big 5 facets)

# Load Dataset
df_facet_compare = pd.read_csv('Entrepreneurs_and_Employee_Scores_Anon.csv')
df_facet_compare = df_facet_compare.set_index('User')


df_compaer_graph = pd.DataFrame(df_facet_compare.set_index('Target').stack()).reset_index()
df_compaer_graph.columns = ['Target','Personality','Value']
df_compaer_graph['Personality'] = df_compaer_graph['Personality'].apply(lambda x: x.replace('_facet_',' (').replace('_percentile',')').replace('Emotional range','Emotional Stability').replace('_','-'))

# Manipulate the dataset for the figrue
df_sig_comper = df_compaer_graph[df_compaer_graph['Personality'].str.contains('adventurousness|modesty|activity-level|anxiety|immoderation|trust')]
df_sig_comper = pd.concat([df_sig_comper[df_sig_comper['Personality'] == 'Openness (adventurousness)'],
                           df_sig_comper[df_sig_comper['Personality'] == 'Agreeableness (modesty)'],
                           df_sig_comper[df_sig_comper['Personality'] == 'Extraversion (activity-level)'],
                           df_sig_comper[df_sig_comper['Personality'] == 'Emotional Stability (anxiety)'],
                           df_sig_comper[df_sig_comper['Personality'] == 'Emotional Stability (immoderation)'],
                           df_sig_comper[df_sig_comper['Personality'] == 'Agreeableness (trust)']])

# Figure 1B
sns.set(font_scale = 4)
sns.set_style("whitegrid", {'legend.frameon':False})
plt.figure(figsize=(20,35))

           
ax = sns.violinplot(x="Value", y="Personality", hue="Target", 
                    data=df_sig_comper, 
                    palette=['.4', '.8'],
                    split=True, linewidth = 2)

colors = [sns.color_palette("Paired")[1], sns.color_palette("Paired")[0],
          sns.color_palette("Greens")[4], sns.color_palette("Greens")[2],
          sns.color_palette("Paired")[7], sns.color_palette("Paired")[6],
          sns.color_palette("Paired")[9], sns.color_palette("Paired")[8],
          sns.color_palette("Paired")[9], sns.color_palette("Paired")[8],
          sns.color_palette("Greens")[4], sns.color_palette("Greens")[2]]

for ind, violin in enumerate(ax.findobj(PolyCollection)):
    rgb = to_rgb(colors[ind])
    violin.set_facecolor(rgb)

ax.tick_params(axis='x', colors='black')
ax.tick_params(axis='y', colors='black') 
sns.set(font_scale = 4)
plt.setp(ax.collections, alpha=.6)
ax.set(xlabel="Percentile Score of Personality Facet")
ax.set(ylabel=None)
ax.xaxis.set_label_coords(.5, -.06)

ax.legend(loc='center left', bbox_to_anchor=(1, 0.5), facecolor = 'white')
sns.despine(left=True,bottom = True)
plt.margins(x=0, y=0)

fig = ax.get_figure()

Figure 1C (t-SNE 2D plot with six clusters)

df_facet_matrix = pd.read_excel('Founders_Cofounders_Twitter_Personality_Matrix_Anon_diff.xlsx')

df_facet_matrix_raw = df_facet_matrix

df_facet_matrix = df_facet_matrix_raw

# Load and Clean Dataset
#df_facet_matrix = pd.read_excel('Founders and Cofounders with Twitter (40k) - Personality Matrix.xlsx')
df_facet_matrix_filter = df_facet_matrix.loc[:,df_facet_matrix.columns.str.contains('facet') & df_facet_matrix.columns.str.contains('raw_score') | df_facet_matrix.columns.str.contains('User')]
print (df_facet_matrix_filter.shape)
df_facet_matrix_filter = df_facet_matrix_filter.drop_duplicates('User')
print (df_facet_matrix_filter.shape)
df_facet_matrix_filter = df_facet_matrix_filter.set_index('User')
print (df_facet_matrix_filter.shape)
df_facet_matrix_filter = df_facet_matrix_filter[~df_facet_matrix_filter['Openness_facet_adventurousness_raw_score'].isna()]
print (df_facet_matrix_filter.shape)

(42266, 31)
(40580, 31)
(40580, 30)
(32732, 30)

df_facet_matrix_filter = df_facet_matrix_filter.sample(1000)

# Apply t-SNE
RS = 123
# time_start = time.time()
# df_input = df_inno_eco_matrix
tsne = TSNE(random_state=RS).fit_transform(df_facet_matrix_filter)
hopkins(tsne,tsne.shape[0])

Comment

The following code takes very long to run:

# Dendrogram
sns.set(font_scale = 1)
dendrogram = sch.dendrogram(sch.linkage(tsne, method  = "ward"))
plt.title('Dendrogram')
plt.xlabel('Founders')
plt.ylabel('Euclidean distances')
plt.show()

Comment

The following code takes very long to run:

# Number of Cluster Selection

num_cluster_range = list(range(2,31))

# Davies Bouldin Index - The smaller the better
db_score_list = []
for i in num_cluster_range:
    hc_test = AgglomerativeClustering(n_clusters = i, metric = 'euclidean', linkage ='ward')
    y_hc_test = hc_test.fit_predict(tsne)
    db_score_list.append(davies_bouldin_score(tsne, y_hc_test))

# Silhouette Coefficient - The larger the better
sil_score_list = []
for i in num_cluster_range:
    hc_test = AgglomerativeClustering(n_clusters = i, metric = 'euclidean', linkage ='ward')
    y_hc_test = hc_test.fit_predict(tsne)
    sil_score_list.append(silhouette_score(tsne, y_hc_test))

# Calinski Harabas Index - The larger the better
ch_score_list = []
for i in num_cluster_range:
    hc_test = AgglomerativeClustering(n_clusters = i, metric = 'euclidean', linkage ='ward')
    y_hc_test = hc_test.fit_predict(tsne)
    ch_score_list.append(calinski_harabasz_score(tsne, y_hc_test))

# Dunn Index - The larger the better
dunn_score_list = []
for i in num_cluster_range:
    hc_test = AgglomerativeClustering(n_clusters = i, metric = 'euclidean', linkage ='ward')
    y_hc_test = hc_test.fit_predict(tsne)
    dist = pairwise_distances(tsne)
    dunn_score_list.append(dunn(dist, y_hc_test))

pio.templates.default = "plotly_white"
# Create traces
fig = go.Figure()
fig.add_vline(x=6, line_width=1, line_dash="dash", line_color="grey")
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(db_score_list),
                         mode='lines', name='Davies Bouldin Index', 
                         line=dict(color='#d62728', width=2.5)))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(sil_score_list),
                         mode='lines', name='Silhouette Coefficient',
                         line=dict(color='#1f77b4', width=2.5, dash='dash')))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(ch_score_list), 
                         mode='lines', name='Calinski Harabas Index',
                         line=dict(color='#ff7f0e', width=2.5, dash='dashdot')))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(dunn_score_list),
                         mode='lines', name='Dunn Index',
                         line=dict(color='#9467bd', width=2.5, dash='dot')))
fig.update_layout(
#     title='Clustering Quality VS Number of Clusters',
                  xaxis_title='Number of Clusters',
                  yaxis_title='Scaled Scores')
fig.show()

# Hierarchical Clustering
hc = AgglomerativeClustering(n_clusters = 6, metric = 'euclidean', linkage ='ward')

y_hc=hc.fit_predict(tsne)
df_6clusters = df_facet_matrix_filter.copy()
df_6clusters['Hierarchical_label'] = y_hc

# Figure 1C
clustering_colors = ['rgb(230,245,152)','rgb(252,141,89)','rgb(50,136,189)','rgb(213,62,79)','rgb(153,213,148)','rgb(254,224,139)']

df_clustering = pd.concat([df_6clusters.reset_index(), pd.DataFrame(tsne, columns = ['x','y'])], axis = 1)
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].apply(lambda x: str(x).replace('1','6').replace('2','7').replace('3','8').replace('4','9').replace('5','-1').replace('9','1').replace('-1','2').replace('6','3').replace('8','4').replace('7','5'))
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].astype(int)
df_clustering = df_clustering[['x','y','Hierarchical_label']].copy()
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].apply(lambda x: str(x).replace('0','Accomplisher').replace('1','Engineer').replace('2','Leader').replace('3','Developer').replace('4','Operator').replace('5','Fighter'))
df_clustering = df_clustering.sort_values('Hierarchical_label')
df_textbox = df_clustering.groupby('Hierarchical_label')[['x','y']].mean().reset_index()

fig = px.scatter(df_clustering, x="x", y="y", color="Hierarchical_label",
                 hover_data=['Hierarchical_label'], template = "plotly_white",
                 color_discrete_sequence=clustering_colors, 
#                  color_discrete_sequence=px.colors.qualitative.Prism, 
                 opacity = 0.2, width=1000, height=800)
fig.update_layout({
    'plot_bgcolor': 'rgba(0,0,0,0)',
    'paper_bgcolor': 'rgba(0,0,0,0)'
})

fig.update_layout(yaxis=dict(title=''),
                  xaxis=dict(title=''))

fig.update_layout(showlegend=False)

fig.update_xaxes(showline = True, linecolor = 'grey', linewidth = 1, row = 1, col = 1, mirror = True)
fig.update_yaxes(showline = True, linecolor = 'grey', linewidth = 1, row = 1, col = 1, mirror = True)
fig.update_xaxes(title="t-SNE dimension 1", title_font=dict(size=16))
fig.update_yaxes(title="t-SNE dimension 2", title_font=dict(size=16))


for index, text, x,y in df_textbox.itertuples(index=True):
    if (text == 'Accomplisher') or (text == 'Leader'):
        text_edit = '<b>' + text + '</b>'
    elif (text == 'Operator') or (text == 'Developer') or (text == 'Fighter'):
        text_edit = '<b>' + text + '</b>'
    else:
        text_edit = '<b>' + text + '</b>'
    fig.add_annotation(
        x=x, y=y,
        text='                       <br>                       ',
        showarrow=False,
        xref="x",
        yref="y",
        font=dict(
            size=14,
            color='black'
            ),
        align="center",
        bordercolor=clustering_colors[index],
#         bordercolor=px.colors.qualitative.Prism[index],
        borderwidth=0,
        borderpad=8,
#         bgcolor=clustering_colors[index],
#         bgcolor=px.colors.qualitative.Prism[index],
        opacity=0.4
    )
    fig.add_annotation(
        x=x, y=y,
        text=text_edit,
        showarrow=False,
        xref="x",
        yref="y",
        font=dict(
            size=18,
            color='black'
            ),
        align="center",
        opacity=1
    )    
    
fig.update_layout(

#     xaxis=dict(gridcolor='lightgrey'),
    margin=dict(r=50, b=0, t = 50, l=0,pad=20)
)
fig.show()
# fig.write_image("outputFiles/Figure_2c.svg")

Figure 1D (Dendrogram heat map of facets per cluster)

df_facet_percentile_compare = df_facet_matrix_raw

# Load and Clean Dataset
#df_facet_percentile_compare = pd.read_excel('Founders and Cofounders with Twitter (40k) - Personality Matrix.xlsx')
df_facet_percentile_compare_filter = df_facet_percentile_compare.loc[:,df_facet_percentile_compare.columns.str.contains('facet') & df_facet_percentile_compare.columns.str.contains('percentile') | df_facet_percentile_compare.columns.str.contains('User')]
print (df_facet_percentile_compare_filter.shape)
df_facet_percentile_compare_filter = df_facet_percentile_compare_filter.drop_duplicates('User')
print (df_facet_percentile_compare_filter.shape)
df_facet_percentile_compare_filter = df_facet_percentile_compare_filter.set_index('User')
print (df_facet_percentile_compare_filter.shape)
df_facet_percentile_compare_filter = df_facet_percentile_compare_filter[~df_facet_percentile_compare_filter['Openness_facet_adventurousness_percentile'].isna()]
print (df_facet_percentile_compare_filter.shape)

df_clustering = pd.concat([df_6clusters.reset_index(), pd.DataFrame(tsne, columns = ['x','y'])], axis = 1)
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].apply(lambda x: str(x).replace('1','6').replace('2','7').replace('3','8').replace('4','9').replace('5','-1').replace('9','1').replace('-1','2').replace('6','3').replace('8','4').replace('7','5'))
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].astype(int)
df_clustering = df_clustering[['User','Hierarchical_label']].copy()
df_clustering['Hierarchical_label'] = df_clustering['Hierarchical_label'].apply(lambda x: str(x).replace('0','Accomplisher').replace('1','Engineer').replace('2','Leader').replace('3','Developer').replace('4','Operator').replace('5','Fighter'))

df_facet_percentile_compare_filter = df_clustering.merge(df_facet_percentile_compare_filter, how = 'left', left_on = 'User', right_on = 'User')
df_facet_percentile_compare_filter = df_facet_percentile_compare_filter.set_index('User')
df_heatmap_median = df_facet_percentile_compare_filter.groupby('Hierarchical_label').median().T
df_heatmap_median.index = ['{0} ({1})'.format(i.replace('_percentile','').replace('_facet','').replace('Emotional range','Emotional Stability').split('_')[0],'-'.join(i.replace('_percentile','').replace('_facet','').replace('Emotional range','Emotional Stability').split('_')[1:])) for i in df_heatmap_median.index.tolist()]

# Figure 1D
im = sns.clustermap(df_heatmap_median, cmap='Greens', linewidth = 1)
ax = im.ax_heatmap
ax.set_xlabel("")
labels = ['Engineer','Fighter','Developer','Operator','Accomplisher','Leader']
ax.set_xticklabels(labels, rotation=90, ha='center')
plt.show()
fig = ax.get_figure()

Supplement

Extended Data Figure 4 (Cohen’s D)

# Extended Data Figure 4
# Load Dataset
df_facet_compare_entrepreneur = pd.read_csv('Entrepreneurs_and_Employee_Scores_Anon.csv')
df_facet_compare_entrepreneur = df_facet_compare_entrepreneur.set_index('User')

#measure cohens d function
def cohen_d(x,y):
    nx = len(x)
    ny = len(y)
    dof = nx + ny - 2
    return (np.mean(x) - np.mean(y)) / np.sqrt(((nx-1)*np.std(x, ddof=1) ** 2 + (ny-1)*np.std(y, ddof=1) ** 2) / dof)

# Organize the results
facet_test_list = []
for facet in df_facet_compare_entrepreneur.columns.tolist()[:30]:
    row_dict = {}
    boss_sample = df_facet_compare_entrepreneur[df_facet_compare_entrepreneur['Target'] == 'Entrepreneur'][facet].tolist()
    employee_sample = df_facet_compare_entrepreneur[df_facet_compare_entrepreneur['Target'] == 'Employee'][facet].tolist()
    row_dict['Big 5 Personality Facets'] = facet
    row_dict["Cohen's D"] = cohen_d(boss_sample, employee_sample)
    res = scipy.stats.ttest_ind(boss_sample, employee_sample, equal_var=False)
    row_dict['p Value'] = res.pvalue
    facet_test_list.append(row_dict)
    
df_facets_cohen_d = pd.DataFrame(facet_test_list)
df_facets_cohen_d['abs_cohen_d'] = df_facets_cohen_d["Cohen's D"].apply(lambda x: np.abs(x))

df_facets_cohen_d.sort_values('abs_cohen_d', ascending = False)
df_facets_cohen_d['Effect Size'] = np.nan
df_facets_cohen_d.loc[(df_facets_cohen_d['abs_cohen_d'] <= 0.2), 'Effect Size'] = 'Trivial'
df_facets_cohen_d.loc[(df_facets_cohen_d['abs_cohen_d'] > 0.2) & (df_facets_cohen_d['abs_cohen_d'] <= 0.4), 'Effect Size'] = 'Small'
df_facets_cohen_d.loc[(df_facets_cohen_d['abs_cohen_d'] > 0.4) & (df_facets_cohen_d['abs_cohen_d'] <= 0.65), 'Effect Size'] = 'Medium'
df_facets_cohen_d.loc[(df_facets_cohen_d['abs_cohen_d'] > 0.65), 'Effect Size'] = 'Large'
df_facets_cohen_d = df_facets_cohen_d.sort_values('abs_cohen_d', ascending = False)
df_facets_cohen_d = df_facets_cohen_d[['Big 5 Personality Facets', "Cohen's D", 'p Value', 'Effect Size']]

df_facets_cohen_d

	Big 5 Personality Facets	Cohen's D	p Value	Effect Size
1	Openness_facet_adventurousness_percentile	0.920176	0.000000e+00	Large
21	Agreeableness_facet_modesty_percentile	-0.792602	0.000000e+00	Large
13	Extraversion_facet_activity_level_percentile	0.776164	0.000000e+00	Large
26	Emotional range_facet_anxiety_percentile	-0.770742	0.000000e+00	Large
28	Emotional range_facet_immoderation_percentile	-0.734884	0.000000e+00	Large
24	Agreeableness_facet_trust_percentile	0.720660	0.000000e+00	Large
25	Emotional range_facet_anger_percentile	-0.679333	8.705857e-279	Large
27	Emotional range_facet_depression_percentile	-0.677018	1.784581e-262	Large
20	Agreeableness_facet_cooperation_percentile	0.669759	1.558560e-285	Large
3	Openness_facet_emotionality_percentile	-0.666483	7.568027e-281	Large
7	Conscientiousness_facet_achievement_striving_p...	0.587171	1.032597e-224	Medium
11	Conscientiousness_facet_self_discipline_percen...	0.548171	4.828852e-186	Medium
8	Conscientiousness_facet_cautiousness_percentile	0.503654	2.582571e-168	Medium
5	Openness_facet_intellect_percentile	0.446235	6.599245e-133	Medium
12	Conscientiousness_facet_self_efficacy_percentile	0.433243	1.990471e-125	Medium
14	Extraversion_facet_assertiveness_percentile	0.431710	4.392563e-122	Medium
6	Openness_facet_liberalism_percentile	0.426033	1.113057e-119	Medium
23	Agreeableness_facet_sympathy_percentile	-0.425556	2.378425e-108	Medium
9	Conscientiousness_facet_dutifulness_percentile	0.412815	2.876272e-110	Medium
10	Conscientiousness_facet_orderliness_percentile	0.308178	2.537543e-63	Small
17	Extraversion_facet_friendliness_percentile	0.236295	1.677218e-34	Small
16	Extraversion_facet_excitement_seeking_percentile	-0.214609	1.261846e-30	Small
29	Emotional range_facet_self_consciousness_perce...	-0.163301	9.374383e-18	Trivial
4	Openness_facet_imagination_percentile	-0.152506	1.906209e-16	Trivial
18	Extraversion_facet_gregariousness_percentile	0.145971	2.537291e-14	Trivial
22	Agreeableness_facet_morality_percentile	0.122673	3.144615e-11	Trivial
15	Extraversion_facet_cheerfulness_percentile	-0.082933	1.014100e-05	Trivial
2	Openness_facet_artistic_interests_percentile	0.044849	1.455970e-02	Trivial
19	Agreeableness_facet_altruism_percentile	-0.044765	1.793611e-02	Trivial
0	Unnamed: 0	-0.018811	3.314753e-01	Trivial

Extended Data Figure 5 (Entrepreneurial Personality Facets)

# Extended Data Figure 5
df_entrepreneurship_heatmap = df_facet_compare_entrepreneur.groupby('Target').median().T.tail(30)
im = sns.clustermap(df_entrepreneurship_heatmap, cmap='Greens')
plt.show()

Extended Data Figure 6 (Hopkins Statistic)

# Extended Data Figure 6

# Dictionary to store the Results 
hopkins_score_dict = {}

# Car Dataset
df_car = pd.read_csv('https://raw.githubusercontent.com/Akankhya123/EDA-on-Car-Features/master/data.csv')
df_car.drop(['Engine Fuel Type', 'Market Category',  'Number of Doors'],axis=1,inplace=True)
df_car = df_car.rename(columns={"Engine HP": "HP", "Engine Cylinders": "Cylinders", "Transmission Type": "Transmission", "Driven_Wheels": "Drive Mode","highway MPG": "MPG-H", "city mpg": "MPG-C", "MSRP": "Price"})
df_car = df_car.drop_duplicates()
df_car = df_car.dropna()
df_car = df_car[['Year', 'HP', 'Cylinders', 'MPG-H', 'MPG-C','Popularity']]
hopkins_score_dict['Car Features'] = 1 - hopkins(df_car.values,df_car.shape[0])

# Athletes Dataset
df_athletes = pd.read_csv('https://raw.githubusercontent.com/flother/rio2016/master/athletes.csv')
df_events = pd.read_csv('https://raw.githubusercontent.com/flother/rio2016/master/events.csv')
df_athletes['sex'] = df_athletes['sex'].apply(lambda x: x.replace('female','1').replace('male','0'))
df_athletes['sex'] = df_athletes['sex'].apply(lambda x: int(x))
df_athletes = df_athletes[['height','weight','gold','silver','bronze','sex']]
df_athletes = df_athletes[~df_athletes['weight'].isna()]
df_athletes = df_athletes[~df_athletes['height'].isna()]
hopkins_score_dict['Olympic Athletes'] = 1 - hopkins(df_athletes.values,df_athletes.shape[0])

# t-sne two dimensions
hopkins_score_dict['2-dimensions'] = 1- hopkins(tsne,tsne.shape[0])

# 32k Founders 30 dimensions
hopkins_score_dict['Founders (32k)'] = 1- hopkins(df_facet_matrix_filter,df_facet_matrix_filter.shape[0])

# Iris Dataset
df_iris = scale(datasets.load_iris().data)
hopkins_score_dict['Irises (test)'] = 1 - hopkins(df_iris,df_iris.shape[0])

# Penguins Dataset
df_penguins,y = load_penguins(return_X_y = True)
df_penguins = df_penguins[~df_penguins['bill_length_mm'].isna()]
hopkins_score_dict['Penguins'] = 1 - hopkins(df_penguins.values,df_penguins.shape[0])

# Random Dataset
df = pd.DataFrame()
for i in df_facet_matrix_filter.columns.tolist():
    new_min = df_facet_matrix_filter[i].min()
    new_max = df_facet_matrix_filter[i].max()
    df[i] = [random() for i in range(df_facet_matrix_filter.shape[0])]
    old_min = df[i].min()
    old_max = df[i].max()
    df[i] = df[i].apply(lambda x: (x-old_min)/(old_max - old_min) * (new_max - new_min) + new_min)
hopkins_score_dict['Random (32k)'] = hopkins(df.values,df.shape[0])

df_hopkins_compare = pd.DataFrame.from_dict(hopkins_score_dict, orient = 'index').reset_index()
df_hopkins_compare.columns = ['Datasets','Hopkins Statistic']

# Extended Data Figure 6
sns.set_style("whitegrid")
cols = ['lightgreen' if (x == '2-dimensions') or (x == 'Founders (32k)') else 'lightgray' for x in df_hopkins_compare['Datasets']]
ax = sns.barplot(x="Datasets", y="Hopkins Statistic", data=df_hopkins_compare, palette=cols)
ax.set(xlabel=None)
ax.set(ylabel=None)
ax.set(title = 'Hopkins Statistic')
sns.despine(left=True)

plt.xticks(rotation=45)

(array([0, 1, 2, 3, 4, 5, 6]),
 [Text(0, 0, 'Car Features'),
  Text(1, 0, 'Olympic Athletes'),
  Text(2, 0, '2-dimensions'),
  Text(3, 0, 'Founders (32k)'),
  Text(4, 0, 'Irises (test)'),
  Text(5, 0, 'Penguins'),
  Text(6, 0, 'Random (32k)')])

Extended Data Figure 7 (Derivation of clusters)

# Extended Data Figure 7
sns.set(font_scale = 1)
dendrogram = sch.dendrogram(sch.linkage(tsne, method  = "ward"))
plt.title('Dendrogram')
plt.xlabel('Founders')
plt.ylabel('Euclidean distances')
plt.show()

Extended Data Figure 8 (Derivation of clusters)

# Extended Data Figure 8
pio.templates.default = "plotly_white"
# Create traces
fig = go.Figure()
fig.add_vline(x=6, line_width=1, line_dash="dash", line_color="grey")
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(db_score_list),
                         mode='lines', name='Davies Bouldin Index', 
                         line=dict(color='#d62728', width=2.5)))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(sil_score_list),
                         mode='lines', name='Silhouette Coefficient',
                         line=dict(color='#1f77b4', width=2.5, dash='dash')))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(ch_score_list), 
                         mode='lines', name='Calinski Harabas Index',
                         line=dict(color='#ff7f0e', width=2.5, dash='dashdot')))
fig.add_trace(go.Scatter(x=num_cluster_range, y=scale(dunn_score_list),
                         mode='lines', name='Dunn Index',
                         line=dict(color='#9467bd', width=2.5, dash='dot')))
fig.update_layout(
#     title='Clustering Quality VS Number of Clusters',
                  xaxis_title='Number of Clusters',
                  yaxis_title='Scaled Scores')
fig.show()

# Extended Data Figure 8
df_6clusters_copy = df_6clusters.copy()
df_6clusters_copy['Hierarchical_label'] = df_6clusters_copy['Hierarchical_label'].apply(lambda x: str(x).replace('1','6').replace('2','7').replace('3','8').replace('4','9').replace('5','-1').replace('9','1').replace('-1','2').replace('6','3').replace('8','4').replace('7','5'))
df_6clusters_copy['Hierarchical_label'] = df_6clusters_copy['Hierarchical_label'].astype(int)
df_counts = pd.DataFrame(df_6clusters_copy['Hierarchical_label'].value_counts())
df_counts = df_counts.reset_index()
df_counts.columns = ['Cluster','Counts']
df_counts['Cluster'] = df_counts['Cluster'].apply(lambda x: str(int(x)))

sns.set_theme(style="white")
ax = sns.barplot(x="Cluster", y="Counts", data=df_counts.sort_values('Cluster'))

Extended Data Figure 19 (Ensemble Model)

## This dataset is a very small subset of the original dataset due to privacy reasons

df_model_v1 = pd.read_csv("ExtendedDataFigure19_Subset.csv")

col_name = df_model_v1.columns.values[1:87]
fmla = "success ~ {0}".format(' + '.join(col_name))

# Run the statistical model
model_v1 = sm.formula.glm(fmla,
                          family=sm.families.Binomial(), data=df_model_v1).fit()
print(model_v1.summary())

# Organize the results as a table
results_as_html = model_v1.summary().tables[1].as_html()
df_results = pd.read_html(results_as_html, header=0, index_col=0)[0]
df_results_plot = df_results[df_results['P>|z|']<0.05].sort_values('coef')
df_results_plot.rename(columns = {'P>|z|':'p-value'}, inplace = True)
df_results_plot = df_results_plot.reset_index()
df_results_plot
df_results_plot['Factors'] = np.nan
df_results_plot.loc[df_results_plot['index'].str.contains('ind_'),'Factors'] = 'Industry'
df_results_plot.loc[df_results_plot['index'].str.contains('combo'),'Factors'] = 'Combination'
df_results_plot.loc[df_results_plot['index'].str.contains('big5_'),'Factors'] = 'big5'
df_results_plot.loc[df_results_plot['index'].str.contains('facet_'),'Factors'] = 'Facets'
df_results_plot['Factors'] = df_results_plot['Factors'].fillna('Others')
# df_results_plot['Error'] = df_results_plot['std err'].apply(lambda x: 2*x)
df_results_plot = pd.concat([df_results_plot[df_results_plot['Factors'] == 'big5'],
                             df_results_plot[df_results_plot['Factors'] == 'Facets'],
                             df_results_plot[df_results_plot['Factors'] == 'Combination'],
                             df_results_plot[df_results_plot['Factors'] == 'Industry'],
                             df_results_plot[df_results_plot['Factors'] == 'Others']])

C:\Users\schoo\anaconda3\lib\site-packages\statsmodels\genmod\families\links.py:198: RuntimeWarning: overflow encountered in exp
  t = np.exp(-z)
C:\Users\schoo\anaconda3\lib\site-packages\statsmodels\genmod\families\family.py:1056: RuntimeWarning: divide by zero encountered in log
  special.gammaln(n - y + 1) + y * np.log(mu / (1 - mu + 1e-20)) +
C:\Users\schoo\anaconda3\lib\site-packages\statsmodels\genmod\families\family.py:1056: RuntimeWarning: invalid value encountered in multiply
  special.gammaln(n - y + 1) + y * np.log(mu / (1 - mu + 1e-20)) +

                 Generalized Linear Model Regression Results                  
==============================================================================
Dep. Variable:                success   No. Observations:                 4152
Model:                            GLM   Df Residuals:                     3968
Model Family:                Binomial   Df Model:                          183
Link Function:                  Logit   Scale:                          1.0000
Method:                          IRLS   Log-Likelihood:                    nan
Date:                Thu, 14 Mar 2024   Deviance:                   1.3023e+05
Time:                        12:18:57   Pearson chi2:                 6.37e+18
No. Iterations:                   100   Pseudo R-squ. (CS):                nan
Covariance Type:            nonrobust                                         
===========================================================================================================================
                                                              coef    std err          z      P>|z|      [0.025      0.975]
---------------------------------------------------------------------------------------------------------------------------
Intercept                                               -2.438e+15   2.71e+07  -8.99e+07      0.000   -2.44e+15   -2.44e+15
org_country[T.AUS]                                       3.036e+15   5.06e+07      6e+07      0.000    3.04e+15    3.04e+15
org_country[T.BGD]                                         24.1838   3.17e-07   7.64e+07      0.000      24.184      24.184
org_country[T.BRA]                                       3.935e+15    5.9e+07   6.67e+07      0.000    3.94e+15    3.94e+15
org_country[T.CAN]                                       3.608e+15   4.91e+07   7.35e+07      0.000    3.61e+15    3.61e+15
org_country[T.CHE]                                       4.586e+15   6.21e+07   7.39e+07      0.000    4.59e+15    4.59e+15
org_country[T.CHL]                                       8.478e+13    5.9e+07   1.44e+06      0.000    8.48e+13    8.48e+13
org_country[T.CHN]                                       8.936e+15   8.63e+07   1.04e+08      0.000    8.94e+15    8.94e+15
org_country[T.COL]                                       9.732e+14   8.57e+07   1.13e+07      0.000    9.73e+14    9.73e+14
org_country[T.CZE]                                      -4.501e+14   8.29e+07  -5.43e+06      0.000    -4.5e+14    -4.5e+14
org_country[T.DEU]                                       3.819e+15   5.04e+07   7.58e+07      0.000    3.82e+15    3.82e+15
org_country[T.DNK]                                       6.694e+14   6.23e+07   1.08e+07      0.000    6.69e+14    6.69e+14
org_country[T.EGY]                                      -1.713e+13   8.36e+07  -2.05e+05      0.000   -1.71e+13   -1.71e+13
org_country[T.ESP]                                        4.23e+15   4.87e+07   8.68e+07      0.000    4.23e+15    4.23e+15
org_country[T.FIN]                                       3.892e+15   5.56e+07   6.99e+07      0.000    3.89e+15    3.89e+15
org_country[T.FRA]                                       3.533e+15   5.01e+07   7.05e+07      0.000    3.53e+15    3.53e+15
org_country[T.GBR]                                       3.626e+15   4.85e+07   7.47e+07      0.000    3.63e+15    3.63e+15
org_country[T.HKG]                                      -6.513e+13   6.81e+07  -9.56e+05      0.000   -6.51e+13   -6.51e+13
org_country[T.IDN]                                       2.491e+15   6.81e+07   3.66e+07      0.000    2.49e+15    2.49e+15
org_country[T.IND]                                       3.621e+15   4.86e+07   7.44e+07      0.000    3.62e+15    3.62e+15
org_country[T.IRL]                                       2.794e+15   5.19e+07   5.39e+07      0.000    2.79e+15    2.79e+15
org_country[T.ISR]                                       3.968e+15   5.17e+07   7.67e+07      0.000    3.97e+15    3.97e+15
org_country[T.ITA]                                      -3.187e+14   5.41e+07  -5.89e+06      0.000   -3.19e+14   -3.19e+14
org_country[T.JPN]                                       4.126e+15   6.79e+07   6.08e+07      0.000    4.13e+15    4.13e+15
org_country[T.KOR]                                       1.881e+15   6.78e+07   2.77e+07      0.000    1.88e+15    1.88e+15
org_country[T.MEX]                                       4.389e+13   6.87e+07   6.39e+05      0.000    4.39e+13    4.39e+13
org_country[T.NGA]                                       1.035e+13   6.22e+07   1.66e+05      0.000    1.03e+13    1.03e+13
org_country[T.NLD]                                       3.249e+15   5.22e+07   6.22e+07      0.000    3.25e+15    3.25e+15
org_country[T.NOR]                                      -3.522e+14    8.3e+07  -4.25e+06      0.000   -3.52e+14   -3.52e+14
org_country[T.NPL]                                      -4.938e+14   8.31e+07  -5.94e+06      0.000   -4.94e+14   -4.94e+14
org_country[T.POL]                                       8.327e+15   8.31e+07      1e+08      0.000    8.33e+15    8.33e+15
org_country[T.PRT]                                       -5.81e+14    8.3e+07     -7e+06      0.000   -5.81e+14   -5.81e+14
org_country[T.ROM]                                       2.789e+15   6.19e+07    4.5e+07      0.000    2.79e+15    2.79e+15
org_country[T.RUS]                                       2.177e+14    6.8e+07    3.2e+06      0.000    2.18e+14    2.18e+14
org_country[T.SGP]                                       4.076e+15   6.24e+07   6.53e+07      0.000    4.08e+15    4.08e+15
org_country[T.SWE]                                       3.678e+15   6.21e+07   5.93e+07      0.000    3.68e+15    3.68e+15
org_country[T.THA]                                       8.203e+15   8.37e+07    9.8e+07      0.000     8.2e+15     8.2e+15
org_country[T.TUR]                                      -5.189e+14   5.92e+07  -8.77e+06      0.000   -5.19e+14   -5.19e+14
org_country[T.UKR]                                      -6.511e+14   6.81e+07  -9.56e+06      0.000   -6.51e+14   -6.51e+14
org_country[T.USA]                                       3.798e+15   4.84e+07   7.85e+07      0.000     3.8e+15     3.8e+15
org_country[T.ZAF]                                      -3.219e+14   6.21e+07  -5.18e+06      0.000   -3.22e+14   -3.22e+14
combo[T.Ac1De1]                                          1.219e+14    1.1e+07    1.1e+07      0.000    1.22e+14    1.22e+14
combo[T.Ac1De1Fi1]                                       4.299e+15   4.85e+07   8.86e+07      0.000     4.3e+15     4.3e+15
combo[T.Ac1De1Op1]                                      -4.193e+15   6.81e+07  -6.15e+07      0.000   -4.19e+15   -4.19e+15
combo[T.Ac1De2]                                         -4.396e+15   6.77e+07  -6.49e+07      0.000    -4.4e+15    -4.4e+15
combo[T.Ac1En1]                                          -8.59e+14   1.77e+07  -4.85e+07      0.000   -8.59e+14   -8.59e+14
combo[T.Ac1En1De1]                                      -5.013e+15   6.94e+07  -7.22e+07      0.000   -5.01e+15   -5.01e+15
combo[T.Ac1En1Fi1]                                      -4.537e+15   6.85e+07  -6.63e+07      0.000   -4.54e+15   -4.54e+15
combo[T.Ac1En2]                                          3.982e+15   6.82e+07   5.84e+07      0.000    3.98e+15    3.98e+15
combo[T.Ac1Fi1]                                          9.658e+13   1.47e+07   6.59e+06      0.000    9.66e+13    9.66e+13
combo[T.Ac1Le1]                                         -6.376e+14    1.4e+07  -4.57e+07      0.000   -6.38e+14   -6.38e+14
combo[T.Ac1Le1De1]                                      -1.828e+15   3.94e+07  -4.64e+07      0.000   -1.83e+15   -1.83e+15
combo[T.Ac1Le2]                                         -6.433e+14   4.82e+07  -1.33e+07      0.000   -6.43e+14   -6.43e+14
combo[T.Ac1Op1]                                          8.138e+14   1.56e+07   5.22e+07      0.000    8.14e+14    8.14e+14
combo[T.Ac1Op1Fi1]                                      -4.298e+15   6.89e+07  -6.24e+07      0.000    -4.3e+15    -4.3e+15
combo[T.Ac2]                                              5.92e+14   1.09e+07   5.41e+07      0.000    5.92e+14    5.92e+14
combo[T.Ac2De1]                                          -4.84e+15   3.93e+07  -1.23e+08      0.000   -4.84e+15   -4.84e+15
combo[T.Ac2En1]                                          6.526e+14    4.9e+07   1.33e+07      0.000    6.53e+14    6.53e+14
combo[T.Ac2Fi1]                                          4.284e+15   6.85e+07   6.25e+07      0.000    4.28e+15    4.28e+15
combo[T.Ac2Le1]                                         -1.883e+15   4.82e+07  -3.91e+07      0.000   -1.88e+15   -1.88e+15
combo[T.Ac2Le1Fi1]                                       2.889e+15   6.93e+07   4.17e+07      0.000    2.89e+15    2.89e+15
combo[T.Ac2Op1]                                         -9.186e+14   4.84e+07   -1.9e+07      0.000   -9.19e+14   -9.19e+14
combo[T.Ac3]                                            -7.823e+14   4.84e+07  -1.62e+07      0.000   -7.82e+14   -7.82e+14
combo[T.De1]                                            -1.457e+13   4.97e+06  -2.93e+06      0.000   -1.46e+13   -1.46e+13
combo[T.De1Fi1]                                         -1.679e+14   1.09e+07  -1.53e+07      0.000   -1.68e+14   -1.68e+14
combo[T.De1Fi2]                                         -1.007e+14   4.03e+07   -2.5e+06      0.000   -1.01e+14   -1.01e+14
combo[T.De1Op1]                                          1.905e+15   1.75e+07   1.09e+08      0.000    1.91e+15    1.91e+15
combo[T.De1Op1Fi1]                                      -4.839e+15   4.91e+07  -9.85e+07      0.000   -4.84e+15   -4.84e+15
combo[T.De2]                                            -2.381e+14   1.25e+07   -1.9e+07      0.000   -2.38e+14   -2.38e+14
combo[T.De2Fi1]                                          2.643e+15   3.96e+07   6.68e+07      0.000    2.64e+15    2.64e+15
combo[T.De2Op1]                                           4.29e+15   6.77e+07   6.33e+07      0.000    4.29e+15    4.29e+15
combo[T.En1]                                            -8.336e+12    6.5e+06  -1.28e+06      0.000   -8.34e+12   -8.34e+12
combo[T.En1De1]                                          5.012e+13   1.22e+07   4.12e+06      0.000    5.01e+13    5.01e+13
combo[T.En1De1Fi1]                                      -7.703e+14   2.91e+07  -2.65e+07      0.000    -7.7e+14    -7.7e+14
combo[T.En1De1Op1]                                       -3.81e+14   3.97e+07  -9.59e+06      0.000   -3.81e+14   -3.81e+14
combo[T.En1De2]                                         -3.599e+15   6.81e+07  -5.29e+07      0.000    -3.6e+15    -3.6e+15
combo[T.En1Fi1]                                          3.359e+14   1.57e+07   2.14e+07      0.000    3.36e+14    3.36e+14
combo[T.En1Fi2]                                         -4.194e+15   6.84e+07  -6.14e+07      0.000   -4.19e+15   -4.19e+15
combo[T.En1Le1]                                         -8.939e+13    1.4e+07   -6.4e+06      0.000   -8.94e+13   -8.94e+13
combo[T.En1Le1De1]                                       4.678e+15   6.92e+07   6.76e+07      0.000    4.68e+15    4.68e+15
combo[T.En1Op1]                                         -5.349e+14   1.95e+07  -2.74e+07      0.000   -5.35e+14   -5.35e+14
combo[T.En2]                                             2.081e+13   1.43e+07   1.46e+06      0.000    2.08e+13    2.08e+13
combo[T.En2De1]                                          -4.72e+15   6.82e+07  -6.92e+07      0.000   -4.72e+15   -4.72e+15
combo[T.En2Fi1]                                         -2.183e+15   4.03e+07  -5.41e+07      0.000   -2.18e+15   -2.18e+15
combo[T.En2Le1]                                          5.344e+15   6.84e+07   7.81e+07      0.000    5.34e+15    5.34e+15
combo[T.En2Op1]                                         -4.692e+15    6.8e+07   -6.9e+07      0.000   -4.69e+15   -4.69e+15
combo[T.Fi1]                                             1.206e+14   7.04e+06   1.71e+07      0.000    1.21e+14    1.21e+14
combo[T.Fi2]                                              7.79e+14   1.21e+07   6.46e+07      0.000    7.79e+14    7.79e+14
combo[T.Fi3]                                            -1.259e+15   4.86e+07  -2.59e+07      0.000   -1.26e+15   -1.26e+15
combo[T.Le1]                                             1.234e+14   5.06e+06   2.44e+07      0.000    1.23e+14    1.23e+14
combo[T.Le1De1]                                         -1.831e+15    1.4e+07  -1.31e+08      0.000   -1.83e+15   -1.83e+15
combo[T.Le1De1Fi1]                                       7.185e+14   4.03e+07   1.78e+07      0.000    7.19e+14    7.19e+14
combo[T.Le1Fi1]                                          1.935e+14   1.44e+07   1.35e+07      0.000    1.93e+14    1.93e+14
combo[T.Le1Fi2]                                         -4.055e+15   6.87e+07   -5.9e+07      0.000   -4.06e+15   -4.06e+15
combo[T.Le1Fi3]                                          4.965e+15   6.93e+07   7.17e+07      0.000    4.97e+15    4.97e+15
combo[T.Le1Op1]                                         -7.439e+14   2.19e+07   -3.4e+07      0.000   -7.44e+14   -7.44e+14
combo[T.Le2]                                            -3.398e+14   1.53e+07  -2.22e+07      0.000    -3.4e+14    -3.4e+14
combo[T.Op1]                                            -2.847e+13   5.68e+06  -5.02e+06      0.000   -2.85e+13   -2.85e+13
combo[T.Op1Fi1]                                          2.194e+14   1.52e+07   1.45e+07      0.000    2.19e+14    2.19e+14
combo[T.Op1Fi2]                                         -4.723e+15   6.81e+07  -6.94e+07      0.000   -4.72e+15   -4.72e+15
combo[T.Op2]                                            -2.421e+14   1.73e+07   -1.4e+07      0.000   -2.42e+14   -2.42e+14
combo[T.Op2Fi1]                                         -4.306e+15   7.16e+07  -6.02e+07      0.000   -4.31e+15   -4.31e+15
olderthansix                                            -2.438e+15   2.71e+07  -8.99e+07      0.000   -2.44e+15   -2.44e+15
Female                                                  -4.659e+14   4.16e+06  -1.12e+08      0.000   -4.66e+14   -4.66e+14
org_numfounders                                          1.398e+14   1.53e+06   9.15e+07      0.000     1.4e+14     1.4e+14
ind_Administrative_Services                             -2.296e+14   8.29e+06  -2.77e+07      0.000    -2.3e+14    -2.3e+14
ind_Advertising                                         -2.608e+13   6.47e+06  -4.03e+06      0.000   -2.61e+13   -2.61e+13
ind_Agriculture_and_Farming                             -4.057e+15   3.91e+07  -1.04e+08      0.000   -4.06e+15   -4.06e+15
ind_Apps                                                -1.953e+14   5.72e+06  -3.41e+07      0.000   -1.95e+14   -1.95e+14
ind_Artificial_Intelligence                             -9.234e+13   1.08e+07  -8.54e+06      0.000   -9.23e+13   -9.23e+13
ind_Biotechnology                                        3.933e+14   1.18e+07   3.34e+07      0.000    3.93e+14    3.93e+14
ind_Clothing_and_Apparel                                 1.932e+14   1.28e+07   1.51e+07      0.000    1.93e+14    1.93e+14
ind_Commerce_and_Shopping                                3.221e+14   4.23e+06   7.62e+07      0.000    3.22e+14    3.22e+14
ind_Community_and_Lifestyle                              1.256e+14   6.59e+06   1.91e+07      0.000    1.26e+14    1.26e+14
ind_Consumer_Electronics                                -4.886e+14   1.08e+07  -4.54e+07      0.000   -4.89e+14   -4.89e+14
ind_Consumer_Goods                                       6.959e+14   1.21e+07   5.73e+07      0.000    6.96e+14    6.96e+14
ind_Content_and_Publishing                               4.298e+14   6.52e+06   6.59e+07      0.000     4.3e+14     4.3e+14
ind_Data_and_Analytics                                   2.306e+14   5.37e+06    4.3e+07      0.000    2.31e+14    2.31e+14
ind_Design                                              -3.687e+14   8.27e+06  -4.46e+07      0.000   -3.69e+14   -3.69e+14
ind_Education                                           -5.246e+12   4.78e+06   -1.1e+06      0.000   -5.25e+12   -5.25e+12
ind_Energy                                              -4.701e+15   7.73e+07  -6.08e+07      0.000    -4.7e+15    -4.7e+15
ind_Events                                               3.813e+14    1.4e+07   2.72e+07      0.000    3.81e+14    3.81e+14
ind_Financial_Services                                   1.784e+13   5.29e+06   3.37e+06      0.000    1.78e+13    1.78e+13
ind_Food_and_Beverage                                    1.513e+14   8.39e+06    1.8e+07      0.000    1.51e+14    1.51e+14
ind_Gaming                                               5.151e+14   1.07e+07    4.8e+07      0.000    5.15e+14    5.15e+14
ind_Government_and_Military                             -5.076e+14   2.57e+07  -1.97e+07      0.000   -5.08e+14   -5.08e+14
ind_Hardware                                              3.49e+14   6.14e+06   5.68e+07      0.000    3.49e+14    3.49e+14
ind_Health_Care                                          2.069e+14   4.89e+06   4.23e+07      0.000    2.07e+14    2.07e+14
ind_Information_Technology                                3.14e+13   3.44e+06   9.13e+06      0.000    3.14e+13    3.14e+13
ind_Internet_Services                                    1.041e+14   2.97e+06   3.51e+07      0.000    1.04e+14    1.04e+14
ind_Lending_and_Investments                              4.676e+13   9.35e+06      5e+06      0.000    4.68e+13    4.68e+13
ind_Manufacturing                                       -8.783e+14   1.87e+07   -4.7e+07      0.000   -8.78e+14   -8.78e+14
ind_Media_and_Entertainment                             -1.178e+14   5.02e+06  -2.35e+07      0.000   -1.18e+14   -1.18e+14
ind_Messaging_and_Telecommunications                     4.145e+14   9.87e+06    4.2e+07      0.000    4.14e+14    4.14e+14
ind_Mobile                                               2.744e+14   5.08e+06   5.41e+07      0.000    2.74e+14    2.74e+14
ind_Music_and_Audio                                       4.75e+14   9.08e+06   5.23e+07      0.000    4.75e+14    4.75e+14
ind_Natural_Resources                                    4.378e+15   7.19e+07   6.09e+07      0.000    4.38e+15    4.38e+15
ind_Navigation_and_Mapping                              -1.232e+15   2.63e+07  -4.69e+07      0.000   -1.23e+15   -1.23e+15
ind_Other                                               -2.438e+14   3.98e+06  -6.13e+07      0.000   -2.44e+14   -2.44e+14
ind_Payments                                             3.352e+14   9.23e+06   3.63e+07      0.000    3.35e+14    3.35e+14
ind_Platforms                                            -4.84e+14   9.97e+06  -4.85e+07      0.000   -4.84e+14   -4.84e+14
ind_Privacy_and_Security                                -1.772e+15   6.39e+06  -2.77e+08      0.000   -1.77e+15   -1.77e+15
ind_Professional_Services                               -1.445e+14   4.33e+06  -3.34e+07      0.000   -1.44e+14   -1.44e+14
ind_Real_Estate                                           4.78e+13   6.96e+06   6.87e+06      0.000    4.78e+13    4.78e+13
ind_Sales_and_Marketing                                  6.555e+14   5.19e+06   1.26e+08      0.000    6.56e+14    6.56e+14
ind_Science_and_Engineering                             -2.546e+14   9.86e+06  -2.58e+07      0.000   -2.55e+14   -2.55e+14
ind_Software                                             3.499e+14   2.93e+06   1.19e+08      0.000     3.5e+14     3.5e+14
ind_Sports                                              -8.371e+13   7.81e+06  -1.07e+07      0.000   -8.37e+13   -8.37e+13
ind_Sustainability                                       4.078e+14   3.47e+07   1.17e+07      0.000    4.08e+14    4.08e+14
ind_Transportation                                       1.801e+14   8.49e+06   2.12e+07      0.000     1.8e+14     1.8e+14
ind_Travel_and_Tourism                                   1.813e+14   8.42e+06   2.15e+07      0.000    1.81e+14    1.81e+14
ind_Video                                                3.871e+14   8.11e+06   4.77e+07      0.000    3.87e+14    3.87e+14
big5_max_open                                           -1.938e+14   1.26e+07  -1.54e+07      0.000   -1.94e+14   -1.94e+14
big5_max_conscient                                       2.373e+14   1.14e+07   2.08e+07      0.000    2.37e+14    2.37e+14
big5_max_extra                                           8.295e+13   9.66e+06   8.59e+06      0.000    8.29e+13    8.29e+13
big5_max_agree                                           2.838e+14   1.03e+07   2.75e+07      0.000    2.84e+14    2.84e+14
big5_max_neuro                                           2.197e+13   7.24e+06   3.03e+06      0.000     2.2e+13     2.2e+13
Openness_facet_adventurousness_percentile               -1.634e+13   1.31e+07  -1.25e+06      0.000   -1.63e+13   -1.63e+13
Openness_facet_artistic_interests_percentile             1.647e+13   1.35e+07   1.22e+06      0.000    1.65e+13    1.65e+13
Openness_facet_emotionality_percentile                  -2.286e+14    1.4e+07  -1.64e+07      0.000   -2.29e+14   -2.29e+14
Openness_facet_imagination_percentile                   -2.959e+14   1.48e+07     -2e+07      0.000   -2.96e+14   -2.96e+14
Openness_facet_intellect_percentile                      5.425e+12   1.37e+07   3.96e+05      0.000    5.42e+12    5.42e+12
Openness_facet_liberalism_percentile                     5.331e+14   1.34e+07   3.97e+07      0.000    5.33e+14    5.33e+14
Conscientiousness_facet_achievement_striving_percentile  9.033e+14   2.24e+07   4.04e+07      0.000    9.03e+14    9.03e+14
Conscientiousness_facet_cautiousness_percentile         -4.928e+13   1.51e+07  -3.27e+06      0.000   -4.93e+13   -4.93e+13
Conscientiousness_facet_dutifulness_percentile           3.585e+14    1.3e+07   2.76e+07      0.000    3.59e+14    3.59e+14
Conscientiousness_facet_orderliness_percentile           3.518e+14   1.27e+07   2.77e+07      0.000    3.52e+14    3.52e+14
Conscientiousness_facet_self_discipline_percentile      -2.151e+14   1.74e+07  -1.24e+07      0.000   -2.15e+14   -2.15e+14
Conscientiousness_facet_self_efficacy_percentile         1.552e+14   1.85e+07   8.37e+06      0.000    1.55e+14    1.55e+14
Extraversion_facet_activity_level_percentile            -4.762e+14   1.85e+07  -2.58e+07      0.000   -4.76e+14   -4.76e+14
Extraversion_facet_assertiveness_percentile             -4.253e+14   1.92e+07  -2.22e+07      0.000   -4.25e+14   -4.25e+14
Extraversion_facet_cheerfulness_percentile               1.039e+15   1.39e+07   7.48e+07      0.000    1.04e+15    1.04e+15
Extraversion_facet_excitement_seeking_percentile         -6.25e+14   1.52e+07  -4.12e+07      0.000   -6.25e+14   -6.25e+14
Extraversion_facet_friendliness_percentile              -4.842e+14   1.63e+07  -2.96e+07      0.000   -4.84e+14   -4.84e+14
Extraversion_facet_gregariousness_percentile            -2.437e+14   1.48e+07  -1.65e+07      0.000   -2.44e+14   -2.44e+14
Agreeableness_facet_altruism_percentile                 -1.505e+13   1.64e+07  -9.19e+05      0.000   -1.51e+13   -1.51e+13
Agreeableness_facet_cooperation_percentile              -2.434e+14   1.98e+07  -1.23e+07      0.000   -2.43e+14   -2.43e+14
Agreeableness_facet_modesty_percentile                  -8.832e+14   1.36e+07  -6.47e+07      0.000   -8.83e+14   -8.83e+14
Agreeableness_facet_morality_percentile                 -5.459e+14   1.42e+07  -3.84e+07      0.000   -5.46e+14   -5.46e+14
Agreeableness_facet_sympathy_percentile                  5.944e+14    1.2e+07   4.94e+07      0.000    5.94e+14    5.94e+14
Agreeableness_facet_trust_percentile                     5.312e+14   1.84e+07   2.88e+07      0.000    5.31e+14    5.31e+14
Emotional_range_facet_anger_percentile                  -4.276e+14   1.47e+07  -2.91e+07      0.000   -4.28e+14   -4.28e+14
Emotional_range_facet_anxiety_percentile                -4.447e+13   1.84e+07  -2.41e+06      0.000   -4.45e+13   -4.45e+13
Emotional_range_facet_depression_percentile               6.73e+14   1.82e+07   3.69e+07      0.000    6.73e+14    6.73e+14
Emotional_range_facet_immoderation_percentile           -3.093e+14   1.17e+07  -2.65e+07      0.000   -3.09e+14   -3.09e+14
Emotional_range_facet_self_consciousness_percentile     -1.841e+14   1.63e+07  -1.13e+07      0.000   -1.84e+14   -1.84e+14
===========================================================================================================================

## Extended Data Figure 19
color_list = [sns.color_palette("Paired").as_hex()[1], sns.color_palette("Paired").as_hex()[5], 
              sns.color_palette("Greens").as_hex()[4], 
              sns.color_palette("Paired").as_hex()[7], sns.color_palette("Paired").as_hex()[9]]

fig = px.bar(df_results_plot, opacity = 0.6,
             x="index", y="coef",template = "plotly_white", 
             color = 'Factors', color_discrete_sequence = color_list,
             width=1500, height=900).update_traces(
    error_y={
        "type": "data",
        "symmetric": True,
        'color':'grey',
        "array": df_results_plot["std err"]
    }
)

fig.update_layout(title=go.layout.Title(text="Coefficient Estimates of Startups Success Model <br><sup>Specification: Success ~ Basics + Country + Personal level + Multi-Founder + Industry + Personality Combo</sup>", 
                                        font=dict(
                                            size=24,
                                            color="#000000")))
fig.update_yaxes(title=None)
fig.update_xaxes(title=None, tickangle=-45, tickfont=dict(color='black', size=14))
fig.update_layout(
    margin=dict(r=2, b=50, pad=20)
)
# fig.update_layout(yaxis_visible=False)